Jonathan Vincent

TL;DR: Results on the dynamic sequences from the TUM dataset using RTAB-Map as visual SLAM suggest that the approach achieves similar localization performance compared to other state-of-the-art methods, while also providing the position of the tracked dynamic objects, a 3D map free of those dynamic objects.

TL;DR: The Open embeddeD Audition System (ODAS) as discussed by the authors is a low-cost embedded computing system for robot audition that includes strategies to reduce the computational load and perform robot audition tasks.

TL;DR: The solution presented in this paper is to train a neural network on pairs of microphones with different spacing and acoustic environmental conditions, and then use this network to estimate a time-frequency mask from all the pairs of microphone forming the array with an arbitrary shape, which is used to perform generalized eigenvalue (GEV) beamforming.

TL;DR: SMP-PHAT as discussed by the authors performs direction of arrival (DoA) of sound estimation with a microphone array by merging pairs of microphones that are parallel in space, which reduces the number of pairwise cross-correlation computations, and brings down the amount of lookup time when searching for DoA.